A dynamic programming inspired outlier rejection algorithm for image mosaicing problem

2021 ◽  
Author(s):  
Christopher S. Smith ◽  
Semih C. Dinc
Keyword(s):  
Dynamic Programming ◽  
Outlier Rejection ◽  
Image Mosaicing ◽  
Rejection Algorithm

scholarly journals Ar Color Grab – A Coloring Experience for Autistic Children

2020 ◽  
Vol 9 (1) ◽  
pp. 696-699
Keyword(s):  
Augmented Reality ◽  
Surface Deformation ◽  
Video Stream ◽  
Autistic Children ◽  
Outlier Rejection ◽  
Rejection Algorithm ◽  
Real Environment ◽  
To Come ◽  
Audio Video ◽  
The Impact

Augmented Reality (AR) brings together a hub of technologies together, thus allowing us to visualize computer generated data over reality. AR enhances the view by adding digital components to the view. Computer added elements are placed over a real environment indirectly by the use of AR, which increases the impact on the viewer. Various forms of elements like audio, video, animation or data may be added on the scene. The gap between the real environment and digital enhancements is bridged by Augmented Reality by creating an exciting situation. Therefore, a colouring book app, which leverages the use of Augmented Reality is presented, the app allows children to colour the characters of the colouring book, which can then be verified by a mobile device. The detection and tracking of the drawing are done using the application, and a 3-D view of the character is animated via a video stream. This video stream is developed according to the colouring done by a child. The visible and omitted regions of the 3D character are projected from the 2-D view using a process which is then presented in reality. A new outlier rejection algorithm is implemented to track a deformable surface for coloured drawings. Real time tracking and surface deformation recovery are provided. A pipeline that creates 2-D and 3- D content is effectively presented. The principal idea behind this project is to come up with an enhanced colouring experience for autistic children using AR, and also enable them to learn something out of it via a video option given by the application.

Theoretical Development of a Modified RANSAC Algorithm for Identifying Outliers in Road Surface Data

2017 ◽  
Author(s):  
Savio J. Pereira ◽  
Craig T. Altmann ◽  
John B. Ferris
Keyword(s):  
Road Surface ◽  
Theoretical Development ◽  
Smooth Transition ◽  
Surface Measurement ◽  
Outlier Rejection ◽  
Rejection Algorithm ◽  
Surface Data ◽  
Data Points ◽  
The Cost ◽  
Ransac Algorithm

Modeling and simulation of vehicles can be improved by using actual road surface data acquired by Road Surface Measurement Systems. Due to inherent properties of the sensors used, the data acquired is often ridden with outliers. This work addresses the issue of identifying and removing outliers by extending the robust outlier rejection algorithm, Random Sampling and Consensus (RANSAC). Specifically, this work modifies the cost function utilized in RANSAC in such a way that it provides a smooth transition for the classification of points as inliers or outliers. The modified RANSAC algorithm is applied to neighborhoods of data points, which are defined as subsets of points that are close to each other based on a distance metric. Based on the outcome of the modified RANSAC algorithm in each neighborhood, a novel measure for determining the likelihood of a point being an outlier, defined in this work as its exogeny, is developed. The algorithm is tested on a simulated road surface dataset. In the future this novel algorithm will also be tested on real-world road surface datasets to evaluate its performance.

Sign in / Sign up

Export Citation Format

Share Document